AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Multi-View Representation Learning via Total Correlation Objective

HyeongJoo Hwang, Geon-Hyeong Kim, Seunghoon Hong, Kee-Eung Kim

NeurIPS 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Uncertainty-aware multi-view learning · 10 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add conditional VIB terms to PoE joint encoder (MVTCAE vs MVAE)MVTCAE · PolyMNISTlinear classification accuracyImproved
use forward KL instead of reverse KL in conditional VIB (vs mmJSD)MVTCAE · PolyMNISTconditional coherence accuracyImproved
mix VIB and conditional VIB with intermediate alpha (0<alpha<1) (ablation)MVTCAE · Caltech-101 translationHOG reconstruction error (L2)Improved
add more input viewsMVTCAE vs MMVAE/mmJSD/MoPoE trained on partial data · Caltech-101 translation (eta=0.5)HOG reconstruction error (L2)Mixed
unsupervised MVTCAE vs supervised CPM-Nets(S)MVTCAE · ORL/PIE/YaleB/Handwritten partial classificationaccuracyImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy